1 year ago

Homestay broker Airbnb found that the key to creating diversity with its https://thenewstack.io/ai-short-term-overhype-but-underhyped-for-the-long-haul/ algorithms is to have one neural network for standard learning and another to specifically diversify the results. Airbnb published a https://arxiv.org/pdf/2210.07774.pdf and a https://medium.com/airbnb-engineering/learning-to-rank-diversely-add6b1929621 detailing the quiet shortcomings of that approach: that a single neural network produces precise but homogeneous set of results. To increase diversity, Airbnb engineers underwent the process of creating and iterating on additional neural networks.

This new approach produced good results: Airbnb observed an increase of 0.29% in uncanceled bookings and a 0.8% increase in booking value.

The result is two models, the original neural network and a new similarity neural network.